# TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification

arXiv: https://arxiv.org/abs/2310.11607 · HTML: https://mlsanity.com/paper/2310.11607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [Benchmarking Natural Language Understanding Services for building Conversational Agents](https://mlsanity.com/paper/1903.05566/) (2019)
- [An Overview of Deep Semi-Supervised Learning](https://mlsanity.com/paper/2006.05278/) (2020)
- [Spreading vectors for similarity search](https://mlsanity.com/paper/1806.03198/) (2018)
- [Large Margin Deep Networks for Classification](https://mlsanity.com/paper/1803.05598/) (2018)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Training Vision Transformers for Image Retrieval](https://mlsanity.com/paper/2102.05644/) (2021)
- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [Deep Open Intent Classification with Adaptive Decision Boundary](https://mlsanity.com/paper/2012.10209/) (2020)
- [Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training](https://mlsanity.com/paper/2106.08616/) (2021)
- [Zero-Shot Text Classification with Self-Training](https://mlsanity.com/paper/2210.17541/) (2022)
- [ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification](https://mlsanity.com/paper/2305.09269/) (2023)
- [Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification](https://mlsanity.com/paper/1805.06118/) (2018)
- [Learning to Classify Open Intent via Soft Labeling and Manifold Mixup](https://mlsanity.com/paper/2204.07804/) (2022)

## Abstract (arXiv)

The ability to detect intent in dialogue systems has become increasingly important in modern technology. These systems often generate a large amount of unlabeled data, and manually labeling this data requires substantial human effort. Semi-supervised methods attempt to remedy this cost by using a model trained on a few labeled examples and then by assigning pseudo-labels to further a subset of unlabeled examples that has a model prediction confidence higher than a certain threshold. However, one particularly perilous consequence of these methods is the risk of picking an imbalanced set of examples across classes, which could lead to poor labels. In the present work, we describe Top-K K-Nearest Neighbor (TK-KNN), which uses a more robust pseudo-labeling approach based on distance in the embedding space while maintaining a balanced set of pseudo-labeled examples across classes through a ranking-based approach. Experiments on several datasets show that TK-KNN outperforms existing models, particularly when labeled data is scarce on popular datasets such as CLINC150 and Banking77. Code is available at https://github.com/ServiceNow/tk-knn